Training samples for deep learning networks are typically obtained through various field experiments, which require significant manpower, resource and time consumption. However, it is possible to utilize simulated data to augment the training samples. In this paper, by comparing the actual experimental model with the simulated model generated by the gprMax [1] forward simulation method, the feasibility of obtaining simulated samples through gprMax simulation is validated. Subsequently, the samples generated by gprMax forward simulation are used for training the network to detect objects in existing real samples. At the same time, aiming at the detection and intelligent recognition of road sub-surface defects, the Swin-YOLOX algorithm is introduced, and the excellence of the detection network, which is improved by augmenting the simulated samples with real samples, is further verified. By comparing the prediction performance of the object detection models, it is observed that the model trained with mixed samples achieved a recall of 94.74% and a mean average precision (mAP) of 97.71%, surpassing the model trained only on real samples by 12.95% and 15.64%, respectively. The feasibility and excellence of training the model with mixed samples are confirmed. The potential of using a fusion of simulated and existing real samples instead of repeatedly acquiring new real samples by field experiment is demonstrated by this study, thereby improving detection efficiency, saving resources, and providing a new approach to the problem of multiple interpretations in ground penetrating radar (GPR) data.

The accurate prediction of bearing capacity is crucial in ensuring the structural integrity and safety of pile foundations. This research compares the Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM) algorithms utilizing a data set of 257 dynamic pile load tests for the first time. Also, this research illustrates the multicollinearity effect on DNN, CNN, RNN, LSTM, and BiLSTM models’ performance and accuracy for the first time. A comprehensive comparative analysis is conducted, employing various statistical performance parameters, rank analysis, and error matrix to evaluate the performance of these models. The performance is further validated using external validation, and visual interpretation is provided using the regression error characteristics (REC) curve and Taylor diagram. Results from the comparative analysis reveal that the DNN (Coefficient of determination (R²)_{training (TR)} = 0.97, root mean squared error (RMSE)_TR = 0.0413; R²_{testing (TS)} = 0.9, RMSE_TS = 0.08) followed by BiLSTM (R²_TR = 0.91, RMSE_TR = 0.782; R²_TS = 0.89, RMSE_TS = 0.0862) model demonstrates the highest performance accuracy. It is noted that the BiLSTM model is better than LSTM because the BiLSTM model, which increases the amount of information for the network, is a sequence processing model made up of two LSTMs, one of which takes the input in a forward manner, and the other in a backward direction. The prediction of pile-bearing capacity is strongly influenced by ram weight (having a considerable multicollinearity level), and the effect of the considerable multicollinearity level has been determined for the model based on the recurrent neural network approach. In this study, the recurrent neural network model has the least performance and accuracy in predicting the pile-bearing capacity.

Shield tunnel lining is prone to water leakage, which may further bring about corrosion and structural damage to the walls, potentially leading to dangerous accidents. To avoid tedious and inefficient manual inspection, many projects use artificial intelligence (AI) to detect cracks and water leakage. A novel method for water leakage inspection in shield tunnel lining that utilizes deep learning is introduced in this paper. Our proposal includes a ConvNeXt-S backbone, deconvolutional-feature pyramid network (D-FPN), spatial attention module (SPAM). and a detection head. It can extract representative features of leaking areas to aid inspection processes. To further improve the model’s robustness, we innovatively use an inversed low-light enhancement method to convert normally illuminated images to low light ones and introduce them into the training samples. Validation experiments are performed, achieving the average precision (AP) score of 56.8%, which outperforms previous work by a margin of 5.7%. Visualization illustrations also support our method’s practical effectiveness.

To completely solve the problem of fatigue cracking issue of orthotropic steel bridge decks (OSDs), the authors proposed a steel–ultra-high performance concrete (UHPC) lightweight composite deck (LWCD) with closed ribs in 2010. Based on the successful application of that LWCD, an adaptation incorporating an innovative composite deck structure, i.e., the hot-rolled section steel–UHPC composite deck with open ribs (SSD) is proposed in this paper, aiming to simplify the fabrication process as well as to reduce the cost of LWCD. Based on a long-span cable-stayed bridge, a design scheme is proposed and is compared with the conventional OSD scheme. Further, a finite element (FE) calculation is conducted to reflect both the global and local behavior of the SSD scheme, and it is found that the peaked stresses in the SSD components are less than the corresponding allowable values. A static test is performed for an SSD strip specimen to understand the anti-cracking behavior of the UHPC layer under negative bending moments. The static test results indicate that the UHPC layer exhibited a satisfactory tensile toughness, the UHPC tensile strength obtained from the test is 1.8 times the calculated stress by the FE model of the real bridge. In addition, the fatigue stresses of typical fatigue-prone details in the SSD are calculated and evaluated, and the influences of key design parameters on the fatigue performance of the SSD are analyzed. According to the fatigue results, the peaked stress ranges for all of the 10 fatigue-prone details are within the corresponding constant amplitude fatigue limits. Then a fatigue test is carried out for another SSD strip specimen to explore the fatigue behavior of the fillet weld between the longitudinal and transverse ribs. The specimen failed at the fillet weld after equivalent 47.5 million cycles of loading under the design fatigue stress range, indicating that the fatigue performance of the SSD could meet the fatigue design requirement. Theoretical calculations and experiments provide a basis for the promotion and application of this structure in bridge engineering.

Digital fabrication techniques, in recent decades, have provided the basis of a sustainable revolution in the construction industry. However, selecting the digital fabrication method in terms of manufacturability and functionality requirements is a complex problem. This paper presents alternatives and criteria for selection of digital fabrication techniques by adopting the multi-criteria decision-making technique. The alternatives considered in the study are concrete three-dimensional (3D) printing, shotcrete, smart dynamic casting, material intrusion, mesh molding, injection concrete 3D printing, and thin forming techniques. The criteria include formwork utilization, reinforcement incorporation, geometrical complexity, material enhancement, assembly complexity, surface finish, and build area. It demonstrates different multi-criteria decision-making techniques, with both subjective and objective weighting methods. The given ranking is based on the current condition of digital fabrication in the construction industry. The study reveals that in the selection of digital fabrication techniques, the criteria including reinforcement incorporation, build area, and geometrical complexity play a pivotal role, collectively accounting for nearly 70% of the overall weighting. Among the evaluated techniques, concrete 3D printing emerged as the best performer, however the shotcrete and mesh molding techniques in the second and third positions.

This study evaluated the feasibility of using polypropylene fiber (PF) as reinforcement in improving tensile strength behavior of cement-stabilized dredged sediment (CDS). The effects of cement content, water content, PF content and length on the tensile strength and stress–strain behavioral evolutions were evaluated by conducting splitting tensile strength tests. Furthermore, the micro-mechanisms characterizing the tensile strength behavior inside PF-reinforced CDS (CPFDS) were clarified via analyzing macro failure and microstructure images. The results indicate that the highest tensile strengths of 7, 28, 60, and 90 d CPFDS were reached at PF contents of 0.6%, 1.0%, 1.0%, and 1.0%, exhibiting values 5.96%, 65.16%, 34.10%, and 35.83% higher than those of CDS, respectively. Short, 3 mm, PF of showed the best reinforcement efficiency. The CPFDS exhibited obvious tensile strain-hardening characteristic, and also had better ductility than CDS. The mix factor (C_C^a/C_w^b) and time parameter (q_t0(t)) of CDS, and the reinforcement index (k_t-PF) of CPFDS were used to establish the tensile strength prediction models of CDS and CPFDS, considering multiple factors. The PF “bridge effect” and associated cementation-reinforcement coupling actions inside CPFDS were mainly responsible for tensile strength behavior improvement. The key findings contribute to the use of CPFDS as recycled engineering soils.

The derivation and validation of analytical equations for predicting the tensile initial stiffness of thread-fixed one-side bolts (TOBs), connected to enclosed rectangular hollow section (RHS) columns, is presented in this paper. Two unknown stiffness components are considered: the TOBs connection and the enclosed RHS face. First, the trapezoidal thread of TOB, as an equivalent cantilevered beam subjected to uniformly distributed loads, is analyzed to determine the associated deformations. Based on the findings, the thread-shank serial-parallel stiffness model of TOB connection is proposed. For analysis of the tensile stiffness of the enclosed RHS face due to two bolt forces, the four sidewalls are treated as rotation constraints, thus reducing the problem to a two-dimensional plate analysis. According to the load superposition method, the deflection of the face plate is resolved into three components under various boundary and load conditions. Referring to the plate deflection theory of Timoshenko, the analytical solutions for the three deflections are derived in terms of the variables of bolt spacing, RHS thickness, height to width ratio, etc. Finally, the validity of the above stiffness equations is verified by a series of finite element (FE) models of T-stub substructures. The proposed component stiffness equations are an effective supplement to the component-based method.

This paper proposes an accurate, efficient and explainable method for the classification of the surrounding rock based on a convolutional neural network (CNN). The state-of-the-art robust CNN model (EfficientNet) is applied to tunnel wall image recognition. Gaussian filtering, data augmentation and other data pre-processing techniques are used to improve the data quality and quantity. Combined with transfer learning, the generality, accuracy and efficiency of the deep learning (DL) model are further improved, and finally we achieve 89.96% accuracy. Compared with other state-of-the-art CNN architectures, such as ResNet and Inception-ResNet-V2 (IRV2), the presented deep transfer learning model is more stable, accurate and efficient. To reveal the rock classification mechanism of the proposed model, Gradient-weight Class Activation Map (Grad-CAM) visualizations are integrated into the model to enable its explainability and accountability. The developed deep transfer learning model has been applied to support the tunneling of the Xingyi City Bypass in the high mountain area of Guizhou, China, with great results.

Raveling is a common distress of asphalt pavements, defined as the removal of stones from the pavement surface. To predict and assess raveling quantitatively, a cumulative damage model based on an energy dissipation approach has been developed at the meso level. To construct the model, a new test method, the pendulum impact test, was employed to determine the fracture energy of the stone-mastic-stone meso-unit, while digital image analysis and dynamic shear rheometer test were used to acquire the strain rate of specimens and the rheology property of mastic, respectively. Analysis of the model reveals that when the material properties remain constant, the cumulative damage is directly correlated with loading time, loading amplitude, and loading frequency. Specifically, damage increases with superimposed linear and cosine variations over time. A higher stress amplitude results in a more rapidly increasing rate of damage, while a lower load frequency leads to more severe damage within the same loading time. Moreover, an example of the application of the model has been presented, showing that the model can be utilized to estimate failure life due to raveling. The model is able to offer a theoretical foundation for the design and maintenance of anti-raveling asphalt pavements.

The thixotropic structural build-up is crucial in extrusion-based three-dimensional (3D) concrete printing. This paper uses a theoretical model to predict the evolution of static and dynamic yield stress for printed concrete. The model employs a structural kinetics framework to create a time-independent constitutive link between shear stress and shear rate. The model considers flocculation, deflocculation, and chemical hydration to anticipate structural buildability. The reversible and irreversible contributions that occur throughout the build-up, breakdown, and hydration are defined based on the proposed structural parameters. Additionally, detailed parametric studies are conducted to evaluate the impact of model parameters. It is revealed that the proposed model is in good agreement with the experimental results, and it effectively characterizes the structural build-up of 3D printable concrete.

The importance of geometrical control of three dimensional (3D) printable concrete without the support of formwork is widely acknowledged. In this study, a numerical model based on computational fluid dynamics was developed to evaluate the geometrical quality of a 3D printed layer. The numerical results were compared, using image analysis, with physical cross-sectional sawn samples. The influence of printing parameters (printing speed, nozzle height, and nozzle diameter) and the rheological behavior of printed materials (yield stress), on the geometrical quality of one printed layer was investigated. In addition, the yield zone of the printed layer was analyzed, giving insights on the critical factors for geometrical control in 3D concrete printing. Results indicated that the developed model can precisely describe the extrusion process, as well as the cross-sectional quality.

The recycled powder (RP) from construction wastes can be used to partially replace cement in the preparation of reactive powder concrete. In this paper, reactive powder concrete mixtures with RP partially replacing cement, and natural sand instead of quartz, are developed. Standard curing is used, instead of steam curing that is normally requested by standard for reactive powder concrete. The influences of RP replacement ratio (0, 10%, 20%, 30%), silica fume proportion (10%, 15%, 20%), and steel fiber proportion (0, 1%, 2%) are investigated. The effects of RP, silica fume, and steel fiber proportion on compressive strength, elastic modulus, and relative absorption energy are analyzed, and theoretical models for compressive strength, elastic modulus, and relative absorption energy are established. A constitutive model for the uniaxial compressive stress–strain relationship of reactive powder concrete with RP is developed. With the increase of RP replacement ratio from 0% to 30%, the compressive strength decreases by 42% and elastic modulus decreases by 24%.

Three-dimensional concrete printing (3DCP) technology begins to be adopted into construction application worldwide. Recent studies have focused on producing a higher concrete quality and offering a user-friendly construction process. Still, the 3DCP construction cost is unlikely to be lower than that of conventional construction, which is especially important for projects where the cost is sensitive. To broaden the 3DCP construction applications, reduction of the quantity of 3DCP material usage is needed. This work aims to perform structural analysis of several patterns of geometric textured 3DCP shell wall structures. 21 different cantilevered textured patterns of 3DCP shell wall structures were architecturally designed and then subjected to structural analysis by a finite element method (FEM). The results indicated that by designing appropriate patterns, the structural performance to weight ratio could be improved up to 300%. The study therefore offers an innovative design process for constructing 3DCP housing and suggests pre-construction analysis methods for 3DCP shell wall structures.

Quality assurance and maintenance play a crucial role in engineering construction, as they have a significant impact on project safety. One common issue in concrete structures is the presence of defects. To enhance the automation level of concrete defect repairs, this study proposes a computer vision-based robotic system, which is based on three-dimensional (3D) printing technology to repair defects. This system integrates multiple sensors such as light detection and ranging (LiDAR) and camera. LiDAR is utilized to model concrete pipelines and obtain geometric parameters regarding their appearance. Additionally, a convolutional neural network (CNN) is employed with a depth camera to locate defects in concrete structures. Furthermore, a method for coordinate transformation is presented to convert the obtained coordinates into executable ones for a robotic arm. Finally, the feasibility of this concrete defect repair method is validated through simulation and experiments.

This work uses isogeometric analysis (IGA), which is based on nonlocal hypothesis and higher-order shear beam hypothesis, to investigate the static bending and free oscillation of a magneto-electro-elastic functionally graded (MEE-FG) nanobeam subject to elastic boundary constraints (BCs). The magneto-electric boundary condition and the Maxwell equation are used to calculate the variation of electric and magnetic potentials along the thickness direction of the nanobeam. This study is innovative since it does not use the conventional boundary conditions. Rather, an elastic system of straight and torsion springs with controllable stiffness is used to support nanobeams’ beginning and end positions, creating customizable BCs. The governing equations of motion of nanobeams are established by applying Hamilton’s principle and IGA is used to determine deflections and natural frequency values. Verification studies were performed to evaluate the convergence and accuracy of the proposed method. Aside from this, the impact of the input parameters on the static bending and free oscillation of the MEE-FG nanobeam is examined in detail. These findings could be valuable for analyzing and designing innovative structures constructed of functionally graded MEE materials.

Due to the complicated three-dimensional behaviors and testing limitations of reinforced concrete (RC) members in torsion, torsional mechanism exploration and torsional performance prediction have always been difficult. In the present paper, several machine learning models were applied to predict the torsional capacity of RC members. Experimental results of a total of 287 torsional specimens were collected through an overall literature review. Algorithms of extreme gradient boosting machine (XGBM), random forest regression, back propagation artificial neural network and support vector machine, were trained and tested by 10-fold cross-validation method. Predictive performances of proposed machine learning models were evaluated and compared, both with each other and with the calculated results of existing design codes, i.e., GB 50010, ACI 318-19, and Eurocode 2. The results demonstrated that better predictive performance was achieved by machine learning models, whereas GB 50010 slightly overestimated the torsional capacity, and ACI 318-19 and Eurocode 2 underestimated it, especially in the case of ACI 318-19. The XGBM model gave the most favorable predictions with R² = 0.999, RMSE = 1.386, MAE = 0.86, and \overline{\lambda }= 0.976. Moreover, strength of concrete was the most sensitive input parameters affecting the reliability of the predictive model, followed by transverse-to-longitudinal reinforcement ratio and total reinforcement ratio.

Flexural performance of joints is critical for prefabricated structures. This study presents a novel channel steel-bolt (CB) joint for prefabricated subway stations. Full-scale tests are carried out to investigate the flexural behavior of the CB joint under the design loads of the test-case station. In addition, a three dimensional (3D) finite element (FE) model of the CB joint is established, incorporating viscous contact to simulate the bonding and detachment behaviors of the interface between channel steel and concrete. Based on the 3D FE model, the study examines the flexural bearing mechanism and influencing factors for the flexural performance of the CB joint. The results indicate that the flexural behavior of the CB joint exhibits significant nonlinear characteristics, which can be divided into four stages. To illustrate the piecewise linearity of the bending moment-rotational angle curve, a four-stage simplified model is proposed, which is easily applicable in engineering practice. The study reveals that axial force can enhance the flexural capacity of the CB joint, while the preload of the bolt has a negligible effect. The flexural capacity of the CB joint is approximate twice the value of the designed bending moment, demonstrating that the joint is suitable for the test-case station.

Concrete is the most widely utilized material for construction purposes, second only to water, in the ever-increasing need for construction globally. Concrete is a brittle material and possesses a high risk of crack formation and consequent deterioration. Cracking, which allows chemicals to enter and can cause concrete structures to lose their physico-mechanical and durability features. Repairing and rehabilitating concrete structures involves high costs and leads to various repair methods including coating, adhesives, polymers, supplementary cementitious materials (SCMs), and fibers. One of the latest technologies is the use of microorganisms in concrete. These added microorganisms lead to calcite precipitation and thereby heal the cracks effectively. This study presents a comprehensive literature survey on bacteria-included concrete, before which a bibliographic survey is performed using VOSViewer software. In addition to regular bacterial concrete, this study focuses on also using SCMs and fibers in bacterial concrete. A detailed literature review with data representation for various mechanical properties including compressive strength (CS), split tensile strength (SS), and flexure strength (FS), along with durability properties including carbonation, water absorption, resistance against chloride ion penetration, gas permeation, and resistance against cyclic freeze-and-thaw is presented. A study on the use of X-ray computed tomography (XCT) in bacterial concrete is highlighted, and the scope for future research, along with identification of the research gap, is presented.

Reinforced concrete (RC) flat slabs, a popular choice in construction due to their flexibility, are susceptible to sudden and brittle punching shear failure. Existing design methods often exhibit significant bias and variability. Accurate estimation of punching shear strength in RC flat slabs is crucial for effective concrete structure design and management. This study introduces a novel computation method, the jellyfish-least square support vector machine (JS-LSSVR) hybrid model, to predict punching shear strength. By combining machine learning (LSSVR) with jellyfish swarm (JS) intelligence, this hybrid model ensures precise and reliable predictions. The model’s development utilizes a real-world experimental data set. Comparison with seven established optimizers, including artificial bee colony (ABC), differential evolution (DE), genetic algorithm (GA), and others, as well as existing machine learning (ML)-based models and design codes, validates the superiority of the JS-LSSVR hybrid model. This innovative approach significantly enhances prediction accuracy, providing valuable support for civil engineers in estimating RC flat slab punching shear strength.

Regular detection and repair for lining cracks are necessary to guarantee the safety and stability of tunnels. The development of computer vision has greatly promoted structural health monitoring. This study proposes a novel encoder–decoder structure, CrackRecNet, for semantic segmentation of lining segment cracks by integrating improved VGG-19 into the U-Net architecture. An image acquisition equipment is designed based on a camera, 3-dimensional printing (3DP) bracket and two laser rangefinders. A tunnel concrete structure crack (TCSC) image data set, containing images collected from a double-shield tunnel boring machines (TBM) tunnel in China, was established. Through data preprocessing operations, such as brightness adjustment, pixel resolution adjustment, flipping, splitting and annotation, 2880 image samples with pixel resolution of 448 × 448 were prepared. The model was implemented by Pytorch in PyCharm processed with 4 NVIDIA TITAN V GPUs. In the experiments, the proposed CrackRecNet showed better prediction performance than U-Net, TernausNet, and ResU-Net. This paper also discusses GPU parallel acceleration effect and the crack maximum width quantification.

The use of prefabricated vertical drains (PVD) in liquefiable deposits is gaining attention due to enhanced drainage. However, investigations on PVD in mitigating re-liquefaction during repeated shaking events are not available. This study performed a series of shaking table experiments on untreated and PVD-treated specimens prepared with 40% and 60% relative density. Repeated sinusoidal loading was applied with an incremental peak acceleration of 0.1g, 0.2g, 0.3g, and 0.4g, at 5 Hz shaking frequency with 40 s duration. The performance of treated ground was evaluated based on the generation and dissipation of excess pore water pressure (EPWP), induced sand densification, subsidence, and cyclic stress ratio. In addition, the strain accumulated in fresh and exhumed PVD was investigated using geotextile tensile testing apparatus aided with digital image correlation. No evidence of pore pressure was reported up to 0.2g peak acceleration for 40% and 60% relative density specimens. The continuous occurrence of soil densification and drainage medium restrained and delayed the generation of EPWP and expedited the dissipation process. This study demonstrates PVD can mitigate re-liquefaction, without suffering from deterioration, when subjected to medium to high intense repeated shaking events.

In engineering applications, concrete crack monitoring is very important. Traditional methods are of low efficiency, low accuracy, have poor timeliness, and are applicable in only a limited number of scenarios. Therefore, more comprehensive detection of concrete damage under different scenarios is of high value for practical engineering applications. Digital image correlation (DIC) technology can provide a large amount of experimental data, and neural network (NN) can process very rich data. Therefore, NN, including convolutional neural networks (CNN) and back propagation neural networks (BP), can be combined with DIC technology to analyze experimental data of three-point bending of plain concrete and four-point bending of reinforced concrete. In addition, strain parameters can be used for training, and displacement parameters can be added for comprehensive consideration. The data obtained by DIC technology are grouped for training, and the recognition results of NN show that the combination of strain and displacement parameters, i.e., the response of specimen surface and whole body, can make results more objective and comprehensive. The identification results obtained by CNN and BP show that these technologies can accurately identify cracks. The identification results for reinforced concrete specimens are less affected by noise than those of plain concrete specimens. CNN is more convenient because it can identify some features directly from images, recognizing the cracks formed by macro development. BP can issue early warning of the microscopic cracks, but it requires a large amount of data and computation. It can be seen that CNN is more intuitive and efficient in image processing, and is suitable when low accuracy is adequate, while BP is suitable for occasions with greater accuracy requirements. The two tools have advantages in different situations, and together they can play an important role in engineering monitoring.

The stick-slip action of strike-slip faults poses a significant threat to the safety and stability of underground structures. In this study, the north-east area of the Longmenshan fault, Sichuan, provides the geological background; the rheological characteristics of the crustal lithosphere and the nonlinear interactions between plates are described by Burger’s viscoelastic constitutive model and the friction constitutive model, respectively. A large-scale global numerical model for plate squeezing analysis is established, and the seemingly periodic stick-slip action of faults at different crust depths is simulated. For a second model at a smaller scale, a local finite element model (sub-model), the time history of displacement at a ground level location on the Longmenshan fault plane in a stick-slip action is considered as the displacement loading. The integration of these models, creating a multi-scale modeling method, is used to evaluate the crack propagation and mechanical response of a tunnel subjected to strike-slip faulting. The determinations of the recurrence interval of stick-slip action and the cracking characteristics of the tunnel are in substantial agreement with the previous field investigation and experimental results, validating the multi-scale modeling method. It can be concluded that, regardless of stratum stiffness, initial cracks first occur at the inverted arch of the tunnel in the footwall, on the squeezed side under strike-slip faulting. The smaller the stratum stiffness is, the smaller the included angle between the crack expansion and longitudinal direction of the tunnel, and the more extensive the crack expansion range. For the tunnel in a high stiffness stratum, both shear and bending failures occur on the lining under strike-slip faulting, while for that in the low stiffness stratum, only bending failure occurs on the lining.

In this work, a novel refined higher-order shear deformation plate theory is integrated with nonlocal elasticity theory for analyzing the free vibration, bending, and transient behaviors of fluid-infiltrated porous metal foam piezoelectric nanoplates resting on Pasternak elastic foundation with flexoelectric effects. Isogeometric analysis (IGA) and the Navier solution are applied to the problem. The innovation in the present study is that the influence of the in-plane variation of the nonlocal parameter on the free and forced vibration of the piezoelectric nanoplates is investigated for the first time. The nonlocal parameter and material characteristics are assumed to be material-dependent and vary gradually over the thickness of structures. Based on Hamilton’s principle, equations of motion are built, then the IGA approach combined with the Navier solution is used to analyze the static and dynamic response of the nanoplate. Lastly, we investigate the effects of the porosity coefficients, flexoelectric parameters, elastic stiffness, thickness, and variation of the nonlocal parameters on the mechanical behaviors of the rectangular and elliptical piezoelectric nanoplates.

Identifying crack and predicting crack propagation are critical processes for the risk assessment of engineering structures. Most traditional approaches to crack modeling are faced with issues of high computational costs and excessive computing time. To address this issue, we explore the potential of deep learning (DL) to increase the efficiency of crack detection and forecasting crack growth. However, there is no single algorithm that can fit all data sets well or can apply in all cases since specific tasks vary. In the paper, we present DL models for identifying cracks, especially on concrete surface images, and for predicting crack propagation. Firstly, SegNet and U-Net networks are used to identify concrete cracks. Stochastic gradient descent (SGD) and adaptive moment estimation (Adam) algorithms are applied to minimize loss function during iterations. Secondly, time series algorithms including gated recurrent unit (GRU) and long short-term memory (LSTM) are used to predict crack propagation. The experimental findings indicate that the U-Net is more robust and efficient than the SegNet for identifying crack segmentation and achieves the most outstanding results. For evaluation of crack propagation, GRU and LSTM are used as DL models and results show good agreement with the experimental data.

The precise prediction of the fundamental vibrational period for reinforced concrete (RC) buildings with infilled walls is essential for structural design, especially earthquake-resistant design. Machine learning models from previous studies, while boasting commendable accuracy in predicting the fundamental period, exhibit vulnerabilities due to lengthy training times and inherent dependence on pre-trained models, especially when engaging with continually evolving data sets. This predicament emphasizes the necessity for a model that adeptly balances predictive accuracy with robust adaptability and swift data training. The latter should include consistent re-training ability as demanded by real-time, continuously updated data sets. This research implements an optimized Light Gradient Boosting Machine (LightGBM) model, highlighting its augmented predictive capabilities, realized through the astute use of Bayesian Optimization for hyperparameter tuning on the FP4026 research data set, and illuminating its adaptability and efficiency in predictive modeling. The results show that the R² score of LightGBM model is 0.9995 and RMSE is 0.0178, while training speed is 23.2 times faster than that offered by XGBoost and 45.5 times faster than for Gradient Boosting. Furthermore, this study introduces a practical application through a streamlit-powered, web-based dashboard, enabling engineers to effortlessly utilize and augment the model, contributing data and ensuring precise fundamental period predictions, effectively bridging scholarly research and practical applications.

The paper introduces a novel approach for detecting structural damage in full-scale structures using surrogate models generated from incomplete modal data and deep neural networks (DNNs). A significant challenge in this field is the limited availability of measurement data for full-scale structures, which is addressed in this paper by generating data sets using a reduced finite element (FE) model constructed by SAP2000 software and the MATLAB programming loop. The surrogate models are trained using response data obtained from the monitored structure through a limited number of measurement devices. The proposed approach involves training a single surrogate model that can quickly predict the location and severity of damage for all potential scenarios. To achieve the most generalized surrogate model, the study explores different types of layers and hyperparameters of the training algorithm and employs state-of-the-art techniques to avoid overfitting and to accelerate the training process. The approach’s effectiveness, efficiency, and applicability are demonstrated by two numerical examples. The study also verifies the robustness of the proposed approach on data sets with sparse and noisy measured data. Overall, the proposed approach is a promising alternative to traditional approaches that rely on FE model updating and optimization algorithms, which can be computationally intensive. This approach also shows potential for broader applications in structural damage detection.

This study employs a hybrid approach, integrating finite element method (FEM) simulations with machine learning (ML) techniques to investigate the structural performance of double-skin tubular columns (DSTCs) reinforced with glass fiber-reinforced polymer (GFRP). The investigation involves a comprehensive examination of critical parameters, including aspect ratio, concrete strength, number of GFRP confinement layers, and dimensions of steel tubes used in DSTCs, through comparative analyses and parametric studies. To ensure the credibility of the findings, the results are rigorously validated against experimental data, establishing the precision and trustworthiness of the analysis. The present research work examines the use of the columns with elliptical cross-sections and contributes valuable insights into the application of FEM and ML in the design and evaluation of structural systems within the field of structural engineering.

In slurry shield tunneling, the stability of tunnel face is closely related to the filter cake. The cutting of the cutterhead has negative impact on the formation of filter cake. This study focuses on the formation time of dynamic filter cake considering the filtration effect and rotation of cutterhead. Filtration effect is the key factor for slurry infiltration. A multilayer slurry infiltration experiment system is designed to investigate the variation of filtrate rheological property in infiltration process. Slurry mass concentration C_L, soil permeability coefficient k, the particle diameter ratio between soil equivalent grain size and representative diameter of slurry particles d₁₀/D₈₅ are selected as independent design variables to fit the computational formula of filtration coefficient. Based on the relative relation between the mass of deposited particles in soil pores and infiltration time, a mathematical model for calculating the formation time of dynamic filter cake is proposed by combining the formation criteria and formation rate of external filter cake. The accuracy of the proposed model is verified through existing experiment data. Analysis results show that filtration coefficient is positively correlated with slurry mass concentration, while negatively correlated with the soil permeability coefficient and the particle diameter ratio between soil and slurry. As infiltration distance increases, the adsorption capacity of soil skeleton to slurry particles gradually decreases. The formation time of external filter cake is significantly lower than internal filter cake and the ratio is approximately 3.9. Under the dynamic cutting of the cutterhead, the formation time is positively associated with the rotation speed of cutter head, while negatively with the phase angle difference between adjacent cutter arm. The formation rate of external filter cake is greater than 98% when d₁₀/D₈₅≤ 6.1. Properly increasing the content or decreasing the diameter size of solid-phase particles in slurry can promote the formation of filter cake.

This paper proposes design charts for estimating imperative input parameters for continuum approach analysis of the nonlinear dynamic response of piles. Experimental and analytical studies using continuum approach have been conducted on single and 2 × 2 grouped piles under coupled and vertical modes of vibration, for different dynamic forces and pile depth. As these design charts are derived from model piles, the charts have been validated for prototype pile foundations using scaling law. The experimental responses of model piles are scaled up and these responses exhibit good agreement with analytical results. This study also extends to estimation of the errors in computing frequency–amplitude responses with an increase in pile length. It is found that, with an increase in pile length, the errors also increase. The effectiveness of the proposed design charts is also checked with data based on different field setups given in existing literature, and these charts are found to be valid. Thus, the developed design charts can be beneficial in estimating the input parameters for continuum approach analysis for determining the nonlinear responses of pile supported machine foundations.